The Agent Skills Directory

[NO_CODE]: The skill consists entirely of instructional Markdown and configuration files. There are no executable scripts, binaries, or complex build processes that could be used for malicious purposes.
[PROMPT_INJECTION]: The skill is designed to ingest data from external primary sources, creating a potential surface for indirect prompt injection. Evidence Chain: 1. Ingestion points: external primary sources such as official documentation and APIs (SKILL.md). 2. Boundary markers: present in the 'Anti-Patterns' section which warns the agent not to treat external content as instructions. 3. Capability inventory: the skill is authorized to write Markdown files to the repository. 4. Sanitization: relies on instruction-based guardrails rather than technical sanitization. Given these mitigations, the risk is categorized as safe.
[DATA_EXFILTRATION]: The skill is limited to reading primary sources and writing to internal repository files. No unauthorized network communication or sensitive data access patterns were found.

research